{
 "id": "nubuwwat/khatme-nubuwwat-ocr-dataset",
 "owner": "nubuwwat",
 "name": "khatme-nubuwwat-ocr-dataset",
 "downloads": 2110,
 "likes": 2,
 "last_modified": "2026-08-24T14:17:01.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask",
  "text-retrieval",
  "image-to-text"
 ],
 "citation": "@misc{khatme_nubuwwat_ocr,\n  title  = {Khatme-Nubuwwat Urdu OCR Corpus},\n  year   = {2026},\n  note   = {215 Nastaliq volumes (~86.5k pages), structure-tagged OCR with a\n            multi-signal accuracy layer, paired with source page scans},\n  url    = {https://huggingface.co/datasets/nubuwwat/khatme-nubuwwat-ocr-dataset}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "c28815c58e8b3f6a538f1ce4cef6d6052e8f9d4d",
 "stated_evidence": "https://huggingface.co/datasets/nubuwwat/khatme-nubuwwat-ocr-dataset/blob/c28815c58e8b3f6a538f1ce4cef6d6052e8f9d4d/README.md",
 "file_evidence": "https://huggingface.co/datasets/nubuwwat/khatme-nubuwwat-ocr-dataset/tree/c28815c58e8b3f6a538f1ce4cef6d6052e8f9d4d",
 "card_nc": false
}